[D]python 文本读出的问题

2012-02-25 05:46:10 277 阅读 AI 写同款 · GEO 优化AI 选题数据监测一键分发 ›

python之解决字典打印的顺序和从文件读出的字典顺序不一致问题问题：文件中保存的是字典，在运行脚本中读出打印的时候和文件中不一致预期：文件中和脚本中打印的字典是一致的顺序解决：利用json模块loads函数的object_pairs_hook（有序键值对）参数，并将object_pairs_hook赋值为collections模块中的有序字典OrderedDict。运行脚本 f = open("test.txt", "r") r = f.read() print json.loads(r, object_pairs_hook=OrderedDict) 阅读详情

文本里面的内容如下：

JrId: 1
JournalTitle: AADE editors' journal
MedAbbr: AADE Ed J
ISSN: 0160-6999
ESSN:
IsoAbbr: AADE Ed J
NlmId: 7708172
JrId: 2
JournalTitle: AANA journal
MedAbbr: AANA J
ISSN: 0094-6354
ESSN:
IsoAbbr: AANA J
NlmId: 0431420
JrId: 3
JournalTitle: AARN news letter
MedAbbr: AARN News Lett
ISSN: 0001-0197
ESSN:
IsoAbbr: AARN News Lett
NlmId: 1251052

上面的文本我想插入到数据库里面，（7行一组）故想生成：
insert into (JrId,JournalTitle,MedAbbr,ISSN,ESSN,IsoAbbr,NlmId) values(%.....)

刚接触python 还不是很熟悉，下面是我写的有问题的：



#!/usr/bin/python

j=open('J_Entrez1.txt')

while True:

    t=j.readline().strip().split(':')

    if not t:

        break

    col,value = t

    query = "insert into test (`%s`) values (%s)" %(col,'"'+value+'"')

    print query

j.close()

上面得出来的是每一行生成了一条insert：
insert into test (`JrId`) values (" 1")
insert into test (`JournalTitle`) values (" AADE editors' journal")
insert into test (`MedAbbr`) values (" AADE Ed J")
insert into test (`ISSN`) values (" 0160-6999")
insert into test (`ESSN`) values ("")
insert into test (`IsoAbbr`) values (" AADE Ed J")
insert into test (`NlmId`) values (" 7708172")
…………
…………
…………
而我想要的是
insert into (JrId,JournalTitle,MedAbbr,ISSN,ESSN,IsoAbbr,NlmId) values("1"," AADE editors' journal"," AADE Ed J"," 0160-6999",""," AADE Ed J"," 7708172")
…………
…………
…………

想半天还是不知道如何实现。。麻烦高人指点下。

------------------------------
Double行动:
原帖分数:100
加分:100

...全文

跨越平台的“换行”之谜：深入解析Windows与Linux文本文件差异文章摘要：本文探讨了Windows和Linux系统处理文本文件的核心差异——换行符的不同（Windows使用CRLF，Linux使用LF）。通过Python代码实验展示了文本模式与二进制模式读取文件的区别，并提供了C语言实现的"文件格式侦探"工具来检测文件格式。该工具通过二进制模式读取文件前1KB数据，根据是否包含CRLF来判断文件格式，解决跨平台文本处理问题。（149字）阅读详情

小小小小周

脚本语言 37,737 成员 34,208 内容

+ 关注 + 加入社区

切换为时间正序

小小小小周 2012-02-26

打赏
举报

按照这个逻辑,自己写了个比较菜的,继续努力...



#!/usr/bin/python

f = open('J_Entrez2.txt')

LIST_col = []

LIST_value = []

count=0

while True:

#    count = 0

    line = f.readline().strip().split(':')

    if line == ['']:

        break

    col,value = line

    LIST_col.append(col)

    LIST_value.append('"'+value+'"')

#    query = "insert into test (`%s`) values (%s)" %(col,'"'+value+'"')

    count += 1

    if count==7:

        query = "insert into test (%s) values (%s)" %(','.join(LIST_col),','.join(LIST_value))

        print query

        count=0

        LIST_col = []

        LIST_value = []

f.close()

~
~
~



root@zhoujy:/home/zhoujy/0225# python e.py 

insert into test (JrId,JournalTitle,MedAbbr,ISSN,ESSN,IsoAbbr,NlmId) values (" 1"," AADE editors' journal"," AADE Ed J"," 0160-6999",""," AADE Ed J"," 7708172")

insert into test (JrId,JournalTitle,MedAbbr,ISSN,ESSN,IsoAbbr,NlmId) values (" 2"," AANA journal"," AANA J"," 0094-6354",""," AANA J"," 0431420")

insert into test (JrId,JournalTitle,MedAbbr,ISSN,ESSN,IsoAbbr,NlmId) values (" 3"," AARN news letter"," AARN News Lett"," 0001-0197",""," AARN News Lett"," 1251052")

root@zhoujy:/home/zhoujy/0225#

小小小小周 2012-02-26

打赏
举报

感谢三位,后面2位的方法对我来说受益匪浅啊,

结贴.

MainRed 2012-02-26

打赏
举报

测试结果：
insert into (JrId,JournalTitle,MedAbbr,ISSN,ESSN,IsoAbbr,NlmId)values("1","AADE editors' journal","AADE Ed J","0160-6999","","AADE Ed J","7708172")
insert into (JrId,JournalTitle,MedAbbr,ISSN,ESSN,IsoAbbr,NlmId)values("2","AANA journal","AANA J","0094-6354","","AANA J","0431420")
insert into (JrId,JournalTitle,MedAbbr,ISSN,ESSN,IsoAbbr,NlmId)values("3","AARN news letter","AARN News Lett","0001-0197","","AARN News Lett","1251052")

MainRed 2012-02-26

打赏
举报



fin = open('in.txt','r')

fout = open('out.txt','w')

i=0

out = 'insert into ('

values = ')values('

for line in fin.readlines():

    print line

    content = line.split(':')

    if i % 7 == 6:

        out+=content[0].strip()

        values+='"' + content[1].strip() + '"'

        fout.write(out+values+')\n')

        print i

        out = 'insert into ('

        values = ')values('

    else:

        out +=content[0].strip()+','

        values+='"' + content[1].strip() + '"' + ','

    i+=1

fin.close()

fout.close()

panghuhu250 2012-02-26

打赏
举报

想把不同行的数据混合在一行，就要先把他们存起来。



fields = "JrId,JournalTitle,MedAbbr,ISSN,ESSN,IsoAbbr,NlmId"

field_list = fields.split(',')



def dict2cmd(record):

    values = [record[f] for f in field_list]

    return 'insert into ( %s ) values ( "%s" )' % (fields, '","'.join(values))



def file2cmd(f):

    counter = 0

    record = {}

    for line in open(f):

        f, v = line.split(":")

        record[f.strip()] = v.strip()

        counter += 1

        if counter == 7:

            print dict2cmd(record)

            record = {}

            counter = 0

import sys

file2cmd(sys.argv[1])

测试：

C:\Documents and Settings\Owner\My Documents\csdn-code>c:\Python26\python.exe fi
le2cmd.py file2cmd.test
insert into ( JrId,JournalTitle,MedAbbr,ISSN,ESSN,IsoAbbr,NlmId ) values ( "1","
AADE editors' journal","AADE Ed J","0160-6999","","AADE Ed J","7708172" )
insert into ( JrId,JournalTitle,MedAbbr,ISSN,ESSN,IsoAbbr,NlmId ) values ( "2","
AANA journal","AANA J","0094-6354","","AANA J","0431420" )
insert into ( JrId,JournalTitle,MedAbbr,ISSN,ESSN,IsoAbbr,NlmId ) values ( "3","
AARN news letter","AARN News Lett","0001-0197","","AARN News Lett","1251052" )

小小小小周 2012-02-25

打赏
举报

牛啊,非常感谢.

回头我试试,这个对初学者来说高深了,学到不少东西..

libralibra 2012-02-25

打赏
举报

只要你文本文档格式都是7个一组,这个脚本可以读任意多组

lines = open('J_Entrez1.txt').readlines()

ind = -1

cnt = 0

for line in lines:

    if cnt%7==0:

        ind += 1

        exec('dic'+str(ind)+'={}')

    exec('dic'+str(ind)+'[line.strip().split(":")[0]]=line.strip().split(":")[1].strip()')

    cnt += 1



for i in range(ind+1):

    print '+++++NEW LINE++++++++++++++++++'

    first = 'insert into ('

    last = ') values('

    for key in eval('dic'+str(i)+'.keys()'):

        first += key+','

        last += '"'+eval('dic'+str(i)+'[key]')+'",'

    query = first[:-1]+last[:-1]+')'    

    print query

测试结果,就用你的测试文件,一共3组

>>> ================================ RESTART ================================

>>> 

+++++NEW LINE++++++++++++++++++

insert into (MedAbbr,JrId,JournalTitle,ISSN,IsoAbbr,NlmId,ESSN) values("AADE Ed J","1","AADE editors' journal","0160-6999","AADE Ed J","7708172","")

+++++NEW LINE++++++++++++++++++

insert into (MedAbbr,JrId,JournalTitle,ISSN,IsoAbbr,NlmId,ESSN) values("AANA J","2","AANA journal","0094-6354","AANA J","0431420","")

+++++NEW LINE++++++++++++++++++

insert into (MedAbbr,JrId,JournalTitle,ISSN,IsoAbbr,NlmId,ESSN) values("AARN News Lett","3","AARN news letter","0001-0197","AARN News Lett","1251052","")

>>>

[D]python 文本读出的问题

相关推荐